© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112752
    Prev
    Next
    INDEX
    Explanations

    Saying something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     litre
    -0.26
    ัà¸Ķ
    -0.25
    ึ
    -0.25
    æĺ¯æĪij们
    -0.24
    ibi
    -0.24
     disabling
    -0.24
    riad
    -0.24
    itan
    -0.23
    obbled
    -0.23
    @↵
    -0.23
    POSITIVE LOGITS
    UNG
    0.27
    ï¼Į并
    0.26
     avent
    0.25
    åIJĦæł·
    0.25
    inker
    0.25
    erin
    0.25
    ewis
    0.25
    ï¼ĮåĪĻ
    0.24
    ächt
    0.23
     doÄŁ
    0.23
    Activations Density 0.008%

    No Known Activations